dc_address_parser 0.1.0
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- checksums.yaml +7 -0
- data/.gitignore +9 -0
- data/.rspec +2 -0
- data/.ruby-version +1 -0
- data/.travis.yml +5 -0
- data/Gemfile +4 -0
- data/LICENSE.txt +21 -0
- data/README.md +44 -0
- data/Rakefile +6 -0
- data/dc_address_parser.gemspec +28 -0
- data/lib/dc_address_parser.rb +10 -0
- data/lib/dc_address_parser/address.rb +195 -0
- data/lib/dc_address_parser/version.rb +3 -0
- data/script/bootstrap +3 -0
- data/script/cibuild +3 -0
- data/script/console +3 -0
- metadata +158 -0
checksums.yaml
ADDED
@@ -0,0 +1,7 @@
|
|
1
|
+
---
|
2
|
+
SHA1:
|
3
|
+
metadata.gz: 14263a461a3fe0f8d380d0e2694fdf0025332b8e
|
4
|
+
data.tar.gz: 01cca92f544be21c6315868c304b9af79dd6aed4
|
5
|
+
SHA512:
|
6
|
+
metadata.gz: 6b7158a7cb1d8e8e98698977a80bf7bcb8477c702bc0d708f51e7751e50ea711d1cabf1f1cc03b84ea3d8e577e86c9fcfd6aa34eb01ccc9d18dd9f9ed534fd3b
|
7
|
+
data.tar.gz: ce7e8cb159ceaa92d687a8db3e6f4c7216e1a7c42ae1831598d40a25a20f7a4329debf28e256e355a692d31e8cc87664aa7a80f6a923eecec7199b1d6ac117bb
|
data/.gitignore
ADDED
data/.rspec
ADDED
data/.ruby-version
ADDED
@@ -0,0 +1 @@
|
|
1
|
+
2.2.4
|
data/.travis.yml
ADDED
data/Gemfile
ADDED
data/LICENSE.txt
ADDED
@@ -0,0 +1,21 @@
|
|
1
|
+
The MIT License (MIT)
|
2
|
+
|
3
|
+
Copyright (c) 2015 Ben Balter
|
4
|
+
|
5
|
+
Permission is hereby granted, free of charge, to any person obtaining a copy
|
6
|
+
of this software and associated documentation files (the "Software"), to deal
|
7
|
+
in the Software without restriction, including without limitation the rights
|
8
|
+
to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
|
9
|
+
copies of the Software, and to permit persons to whom the Software is
|
10
|
+
furnished to do so, subject to the following conditions:
|
11
|
+
|
12
|
+
The above copyright notice and this permission notice shall be included in
|
13
|
+
all copies or substantial portions of the Software.
|
14
|
+
|
15
|
+
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
|
16
|
+
IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
|
17
|
+
FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
|
18
|
+
AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
|
19
|
+
LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
|
20
|
+
OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
|
21
|
+
THE SOFTWARE.
|
data/README.md
ADDED
@@ -0,0 +1,44 @@
|
|
1
|
+
# DC Address Parser
|
2
|
+
|
3
|
+
*Parses and normalizes Washington, DC street addresses according to the DC Master Address Repository (MAR) standard.*
|
4
|
+
|
5
|
+
[](https://travis-ci.org/benbalter/dc-address-parser)
|
6
|
+
|
7
|
+
## Usage
|
8
|
+
|
9
|
+
```ruby
|
10
|
+
address = DcAddressParser.parse "123 main st n.w."
|
11
|
+
|
12
|
+
address.number
|
13
|
+
=> 123
|
14
|
+
|
15
|
+
address.street_name
|
16
|
+
=> "MAIN"
|
17
|
+
|
18
|
+
address.street_type
|
19
|
+
=> "STREET"
|
20
|
+
|
21
|
+
address.quadrant
|
22
|
+
=> "NW"
|
23
|
+
|
24
|
+
address.to_s
|
25
|
+
"123 MAIN STREET NW"
|
26
|
+
```
|
27
|
+
|
28
|
+
## Address standard
|
29
|
+
|
30
|
+
The Gem conforms to the [DC Master Address Repository (MAR) address standard](http://octo.dc.gov/sites/default/files/dc/sites/octo/publication/attachments/DCGIS-MarAddressStandards.pdf). You can learn more about the MAR in the [MAR FAQ](http://octo.dc.gov/sites/default/files/dc/sites/octo/publication/attachments/DCGIS-MarFAQ.pdf).
|
31
|
+
|
32
|
+
## Looking up addresses in the MAR
|
33
|
+
|
34
|
+
The Gem integrates with the [DC Address Lookup](https://github.com/benbalter/dc-address-lookup) gem. To look up an address in the MAR:
|
35
|
+
|
36
|
+
```ruby
|
37
|
+
address.lookup
|
38
|
+
=> #<DcAddressLookup::Location>
|
39
|
+
```
|
40
|
+
|
41
|
+
## Installing
|
42
|
+
|
43
|
+
1. Add `gem 'dc_address_parser'` to your project's Gemfile
|
44
|
+
2. `bundle install`
|
data/Rakefile
ADDED
@@ -0,0 +1,28 @@
|
|
1
|
+
# coding: utf-8
|
2
|
+
lib = File.expand_path('../lib', __FILE__)
|
3
|
+
$LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
|
4
|
+
require 'dc_address_parser/version'
|
5
|
+
|
6
|
+
Gem::Specification.new do |spec|
|
7
|
+
spec.name = "dc_address_parser"
|
8
|
+
spec.version = DcAddressParser::VERSION
|
9
|
+
spec.authors = ["Ben Balter"]
|
10
|
+
spec.email = ["ben.balter@github.com"]
|
11
|
+
|
12
|
+
spec.summary = "Parses and normalizes Washington, DC street addresses according to the DC Master Address Repository (MAR) standard."
|
13
|
+
spec.homepage = "https://github.com/benbalter/dc-address-parser"
|
14
|
+
spec.license = "MIT"
|
15
|
+
|
16
|
+
spec.files = `git ls-files -z`.split("\x0").reject { |f| f.match(%r{^(test|spec|features)/}) }
|
17
|
+
spec.bindir = "exe"
|
18
|
+
spec.executables = spec.files.grep(%r{^exe/}) { |f| File.basename(f) }
|
19
|
+
spec.require_paths = ["lib"]
|
20
|
+
|
21
|
+
spec.add_dependency "activesupport", "~> 4.2"
|
22
|
+
spec.add_dependency "dc_address_lookup", "~> 0.2"
|
23
|
+
spec.add_development_dependency "bundler", "~> 1.11"
|
24
|
+
spec.add_development_dependency "rake", "~> 10.0"
|
25
|
+
spec.add_development_dependency "rspec", "~> 3.0"
|
26
|
+
spec.add_development_dependency "pry", "~> 0.10"
|
27
|
+
spec.add_development_dependency "webmock", "~> 1.22"
|
28
|
+
end
|
@@ -0,0 +1,195 @@
|
|
1
|
+
module DcAddressParser
|
2
|
+
class Address
|
3
|
+
class InvalidAddress < StandardError; end
|
4
|
+
|
5
|
+
attr_reader :raw_address
|
6
|
+
|
7
|
+
CITY = "WASHINGTON, DC"
|
8
|
+
STREET_TYPES = {
|
9
|
+
"STREET" => "ST",
|
10
|
+
"AVENUE" => "AVE",
|
11
|
+
"BOULEVARD" => "BLVD",
|
12
|
+
"ROAD" => "RD",
|
13
|
+
"PLACE" => "PL",
|
14
|
+
"DRIVE" => "DR",
|
15
|
+
"CIRCLE" => "CIR",
|
16
|
+
"PALZA" => "PLZ",
|
17
|
+
"COURT" => "CT",
|
18
|
+
"ALLEY" => "AL",
|
19
|
+
"TERRACE" => "TER"
|
20
|
+
}
|
21
|
+
|
22
|
+
DIRECTIONS = {
|
23
|
+
"NORTH" => "N",
|
24
|
+
"SOUTH" => "S",
|
25
|
+
"EAST" => "E",
|
26
|
+
"WEST" => "W"
|
27
|
+
}
|
28
|
+
|
29
|
+
NUMBER_REGEX = /\A(\d+)[A-Z]*/
|
30
|
+
NUMBER_SUFFIX_REGEX = /(\d+\/\d+|rear)/i
|
31
|
+
STREET_NAME_REGEX = /([A-Z0-9' ]+)/
|
32
|
+
STREET_TYPE_REGEX = /\b(#{Regexp.union(STREET_TYPES.keys)})\b/
|
33
|
+
STREET_TYPE_ABV_REGEX = /\b(#{Regexp.union(STREET_TYPES.values)})\b/
|
34
|
+
QUADRANT_REGEX = /([NS][EW])/
|
35
|
+
|
36
|
+
REQUIRED_PARTS = [:number, :street_name, :street_type, :quadrant]
|
37
|
+
|
38
|
+
def initialize(raw_address)
|
39
|
+
@raw_address = @address = raw_address
|
40
|
+
normalize!
|
41
|
+
REQUIRED_PARTS.each do |part|
|
42
|
+
raise InvalidAddress, "#{part.to_s.sub("_", " ")} is missing" if send(part).nil?
|
43
|
+
end
|
44
|
+
end
|
45
|
+
|
46
|
+
def number
|
47
|
+
@number ||= match(NUMBER_REGEX).to_i
|
48
|
+
end
|
49
|
+
|
50
|
+
def number_suffix
|
51
|
+
@number_suffix ||= match(/#{number}\s#{NUMBER_SUFFIX_REGEX}/)
|
52
|
+
end
|
53
|
+
alias_method :suffix, :number_suffix
|
54
|
+
|
55
|
+
def street_name
|
56
|
+
@street_name ||= begin
|
57
|
+
street_name = match(
|
58
|
+
/#{number}(-?#{unit_number}|\s#{Regexp.escape number_suffix.to_s})?
|
59
|
+
\s#{STREET_NAME_REGEX}\s#{STREET_TYPE_REGEX}/x, 2)
|
60
|
+
|
61
|
+
if street_name =~ /\A[0-9]+\z/
|
62
|
+
street_name = ActiveSupport::Inflector.ordinalize(street_name).upcase
|
63
|
+
end
|
64
|
+
|
65
|
+
street_name
|
66
|
+
end
|
67
|
+
end
|
68
|
+
alias_method :street, :street_name
|
69
|
+
|
70
|
+
def street_type
|
71
|
+
@street_type ||= match STREET_TYPE_REGEX
|
72
|
+
end
|
73
|
+
|
74
|
+
def quadrant
|
75
|
+
@quadrant ||= match QUADRANT_REGEX
|
76
|
+
end
|
77
|
+
alias_method :quad, :quadrant
|
78
|
+
|
79
|
+
def unit_number
|
80
|
+
@unit_number ||= begin
|
81
|
+
unit_number = match(/\A(\d+)(-|–)?([A-Z])\b/) ||
|
82
|
+
match(/\s(UNIT\s|APT\s|#)([A-Z0-9]+)(\s|\z)/, 2) ||
|
83
|
+
match(/#{quadrant}\s([A-Z0-9]+)\z/)
|
84
|
+
if unit_number =~ /\A\d+\z/
|
85
|
+
unit_number.to_i
|
86
|
+
else
|
87
|
+
unit_number
|
88
|
+
end
|
89
|
+
end
|
90
|
+
end
|
91
|
+
alias_method :unit, :unit_number
|
92
|
+
|
93
|
+
def to_h
|
94
|
+
{
|
95
|
+
number: number,
|
96
|
+
number_suffix: number_suffix,
|
97
|
+
street_name: street_name,
|
98
|
+
street_type: street_type,
|
99
|
+
quadrant: quadrant,
|
100
|
+
unit_number: unit_number,
|
101
|
+
city: CITY
|
102
|
+
}
|
103
|
+
end
|
104
|
+
|
105
|
+
def to_s(include_city=false)
|
106
|
+
parts = to_h
|
107
|
+
if include_city
|
108
|
+
parts[:quadrant] << ","
|
109
|
+
else
|
110
|
+
parts.delete(:city)
|
111
|
+
end
|
112
|
+
parts.values.compact.join(" ")
|
113
|
+
end
|
114
|
+
|
115
|
+
def lookup
|
116
|
+
DcAddressLookup.lookup to_s
|
117
|
+
end
|
118
|
+
|
119
|
+
private
|
120
|
+
|
121
|
+
def normalize!
|
122
|
+
normalize_whitespace
|
123
|
+
normalize_case
|
124
|
+
normalize_ranges
|
125
|
+
normalize_quadrant
|
126
|
+
normalize_street_type
|
127
|
+
normalize_rear
|
128
|
+
normalize_space
|
129
|
+
normalize_mlk
|
130
|
+
normalize_directions
|
131
|
+
normalize_mt
|
132
|
+
split
|
133
|
+
end
|
134
|
+
|
135
|
+
def normalize_whitespace
|
136
|
+
@address = @address.strip.squeeze("\s").squeeze("'")
|
137
|
+
end
|
138
|
+
|
139
|
+
def normalize_case
|
140
|
+
@address = @address.upcase
|
141
|
+
end
|
142
|
+
|
143
|
+
def normalize_ranges
|
144
|
+
@address.gsub!(/\A(\d+)\s?(-|–|&)\s?\d+/, '\1')
|
145
|
+
@address.gsub!(/(\d+), \d+,? and \d+/i, '\1')
|
146
|
+
end
|
147
|
+
|
148
|
+
def normalize_quadrant
|
149
|
+
@address.gsub!(/([NS])\.([EW])\.?/, '\1\2')
|
150
|
+
@address.gsub!(/, ([NS][EW])/, ' \1')
|
151
|
+
end
|
152
|
+
|
153
|
+
def normalize_street_type
|
154
|
+
@address.gsub!(STREET_TYPE_ABV_REGEX, STREET_TYPES.invert)
|
155
|
+
end
|
156
|
+
|
157
|
+
def normalize_rear
|
158
|
+
regex = /\AREAR OF (\d+)/
|
159
|
+
return unless @address =~ regex
|
160
|
+
@address.gsub!(/\AREAR OF (\d+)/, '\1')
|
161
|
+
@address << " REAR"
|
162
|
+
end
|
163
|
+
|
164
|
+
def normalize_space
|
165
|
+
@address.gsub!(/\bSPACE\b/, "UNIT")
|
166
|
+
end
|
167
|
+
|
168
|
+
def normalize_mlk
|
169
|
+
@address.gsub!(/\bM\.?L\.? KING\b/, "MARTIN LUTHER KING")
|
170
|
+
@address.gsub!(/\bJR\./, "JR")
|
171
|
+
end
|
172
|
+
|
173
|
+
def normalize_directions
|
174
|
+
regex = /\b(#{Regexp.union DIRECTIONS.values})(?=\s+|\.)/
|
175
|
+
@address.gsub!(regex, DIRECTIONS.invert)
|
176
|
+
end
|
177
|
+
|
178
|
+
def normalize_mt
|
179
|
+
@address.gsub!(/\bMT\b/, "MOUNT")
|
180
|
+
end
|
181
|
+
|
182
|
+
def split
|
183
|
+
@address = @address.split(";").reject { |s| s.empty? }.first.to_s
|
184
|
+
@address = @address.split(/\bAND\b/).first.to_s.strip
|
185
|
+
@address = @address.split(/\b([NS][EW]),/)[0..1].join
|
186
|
+
end
|
187
|
+
|
188
|
+
def match(regex, number=nil)
|
189
|
+
matches = @address.match(regex)
|
190
|
+
return unless matches
|
191
|
+
return matches[number] if number
|
192
|
+
matches.to_a.last
|
193
|
+
end
|
194
|
+
end
|
195
|
+
end
|
data/script/bootstrap
ADDED
data/script/cibuild
ADDED
data/script/console
ADDED
metadata
ADDED
@@ -0,0 +1,158 @@
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
2
|
+
name: dc_address_parser
|
3
|
+
version: !ruby/object:Gem::Version
|
4
|
+
version: 0.1.0
|
5
|
+
platform: ruby
|
6
|
+
authors:
|
7
|
+
- Ben Balter
|
8
|
+
autorequire:
|
9
|
+
bindir: exe
|
10
|
+
cert_chain: []
|
11
|
+
date: 2015-12-23 00:00:00.000000000 Z
|
12
|
+
dependencies:
|
13
|
+
- !ruby/object:Gem::Dependency
|
14
|
+
name: activesupport
|
15
|
+
requirement: !ruby/object:Gem::Requirement
|
16
|
+
requirements:
|
17
|
+
- - "~>"
|
18
|
+
- !ruby/object:Gem::Version
|
19
|
+
version: '4.2'
|
20
|
+
type: :runtime
|
21
|
+
prerelease: false
|
22
|
+
version_requirements: !ruby/object:Gem::Requirement
|
23
|
+
requirements:
|
24
|
+
- - "~>"
|
25
|
+
- !ruby/object:Gem::Version
|
26
|
+
version: '4.2'
|
27
|
+
- !ruby/object:Gem::Dependency
|
28
|
+
name: dc_address_lookup
|
29
|
+
requirement: !ruby/object:Gem::Requirement
|
30
|
+
requirements:
|
31
|
+
- - "~>"
|
32
|
+
- !ruby/object:Gem::Version
|
33
|
+
version: '0.2'
|
34
|
+
type: :runtime
|
35
|
+
prerelease: false
|
36
|
+
version_requirements: !ruby/object:Gem::Requirement
|
37
|
+
requirements:
|
38
|
+
- - "~>"
|
39
|
+
- !ruby/object:Gem::Version
|
40
|
+
version: '0.2'
|
41
|
+
- !ruby/object:Gem::Dependency
|
42
|
+
name: bundler
|
43
|
+
requirement: !ruby/object:Gem::Requirement
|
44
|
+
requirements:
|
45
|
+
- - "~>"
|
46
|
+
- !ruby/object:Gem::Version
|
47
|
+
version: '1.11'
|
48
|
+
type: :development
|
49
|
+
prerelease: false
|
50
|
+
version_requirements: !ruby/object:Gem::Requirement
|
51
|
+
requirements:
|
52
|
+
- - "~>"
|
53
|
+
- !ruby/object:Gem::Version
|
54
|
+
version: '1.11'
|
55
|
+
- !ruby/object:Gem::Dependency
|
56
|
+
name: rake
|
57
|
+
requirement: !ruby/object:Gem::Requirement
|
58
|
+
requirements:
|
59
|
+
- - "~>"
|
60
|
+
- !ruby/object:Gem::Version
|
61
|
+
version: '10.0'
|
62
|
+
type: :development
|
63
|
+
prerelease: false
|
64
|
+
version_requirements: !ruby/object:Gem::Requirement
|
65
|
+
requirements:
|
66
|
+
- - "~>"
|
67
|
+
- !ruby/object:Gem::Version
|
68
|
+
version: '10.0'
|
69
|
+
- !ruby/object:Gem::Dependency
|
70
|
+
name: rspec
|
71
|
+
requirement: !ruby/object:Gem::Requirement
|
72
|
+
requirements:
|
73
|
+
- - "~>"
|
74
|
+
- !ruby/object:Gem::Version
|
75
|
+
version: '3.0'
|
76
|
+
type: :development
|
77
|
+
prerelease: false
|
78
|
+
version_requirements: !ruby/object:Gem::Requirement
|
79
|
+
requirements:
|
80
|
+
- - "~>"
|
81
|
+
- !ruby/object:Gem::Version
|
82
|
+
version: '3.0'
|
83
|
+
- !ruby/object:Gem::Dependency
|
84
|
+
name: pry
|
85
|
+
requirement: !ruby/object:Gem::Requirement
|
86
|
+
requirements:
|
87
|
+
- - "~>"
|
88
|
+
- !ruby/object:Gem::Version
|
89
|
+
version: '0.10'
|
90
|
+
type: :development
|
91
|
+
prerelease: false
|
92
|
+
version_requirements: !ruby/object:Gem::Requirement
|
93
|
+
requirements:
|
94
|
+
- - "~>"
|
95
|
+
- !ruby/object:Gem::Version
|
96
|
+
version: '0.10'
|
97
|
+
- !ruby/object:Gem::Dependency
|
98
|
+
name: webmock
|
99
|
+
requirement: !ruby/object:Gem::Requirement
|
100
|
+
requirements:
|
101
|
+
- - "~>"
|
102
|
+
- !ruby/object:Gem::Version
|
103
|
+
version: '1.22'
|
104
|
+
type: :development
|
105
|
+
prerelease: false
|
106
|
+
version_requirements: !ruby/object:Gem::Requirement
|
107
|
+
requirements:
|
108
|
+
- - "~>"
|
109
|
+
- !ruby/object:Gem::Version
|
110
|
+
version: '1.22'
|
111
|
+
description:
|
112
|
+
email:
|
113
|
+
- ben.balter@github.com
|
114
|
+
executables: []
|
115
|
+
extensions: []
|
116
|
+
extra_rdoc_files: []
|
117
|
+
files:
|
118
|
+
- ".gitignore"
|
119
|
+
- ".rspec"
|
120
|
+
- ".ruby-version"
|
121
|
+
- ".travis.yml"
|
122
|
+
- Gemfile
|
123
|
+
- LICENSE.txt
|
124
|
+
- README.md
|
125
|
+
- Rakefile
|
126
|
+
- dc_address_parser.gemspec
|
127
|
+
- lib/dc_address_parser.rb
|
128
|
+
- lib/dc_address_parser/address.rb
|
129
|
+
- lib/dc_address_parser/version.rb
|
130
|
+
- script/bootstrap
|
131
|
+
- script/cibuild
|
132
|
+
- script/console
|
133
|
+
homepage: https://github.com/benbalter/dc-address-parser
|
134
|
+
licenses:
|
135
|
+
- MIT
|
136
|
+
metadata: {}
|
137
|
+
post_install_message:
|
138
|
+
rdoc_options: []
|
139
|
+
require_paths:
|
140
|
+
- lib
|
141
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
142
|
+
requirements:
|
143
|
+
- - ">="
|
144
|
+
- !ruby/object:Gem::Version
|
145
|
+
version: '0'
|
146
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
147
|
+
requirements:
|
148
|
+
- - ">="
|
149
|
+
- !ruby/object:Gem::Version
|
150
|
+
version: '0'
|
151
|
+
requirements: []
|
152
|
+
rubyforge_project:
|
153
|
+
rubygems_version: 2.5.1
|
154
|
+
signing_key:
|
155
|
+
specification_version: 4
|
156
|
+
summary: Parses and normalizes Washington, DC street addresses according to the DC
|
157
|
+
Master Address Repository (MAR) standard.
|
158
|
+
test_files: []
|